Evaluation - task1-intertass-ES
1899 tweets in qrel, 1899 tweets in run.

Accuracy: 0.599

Confusion matrix
Real	Pred.	#
N	N	585
N	P	100
N	NONE	50
N	NEU	32
NEU	P	71
NEU	N	98
NEU	NEU	18
NEU	NONE	29
NONE	N	91
NONE	NONE	82
NONE	P	86
NONE	NEU	15
P	P	453
P	N	118
P	NEU	26
P	NONE	45

Category evaluation
Cat	P	R	F1
N	0.656	0.763	0.705
NEU	0.198	0.083	0.117
NONE	0.398	0.299	0.342
P	0.638	0.706	0.670

Macro-Precision: 0.472
Macro-Recall: 0.463
Macro-F1: 0.468